AI Client2025

Dyad

Builds apps locally with AI while keeping code, model choices, and deployment paths under the user’s control as a desktop alternative to hosted app builders.

Visit Website

Introduction

AI app builders often trade speed for lock-in. Dyad's bet is that the same conversational app-building loop can work as a local desktop workflow with inspectable code.

What Sets It Apart

Local-first execution changes the privacy and ownership story. Bring-your-own-model support, code export, GitHub/Vercel paths, Supabase integration, MCP extensibility, and security review features make it closer to an app workbench than a prompt demo.

Who Should Use It

Great fit if you want AI-assisted app building with local control and provider flexibility. Look elsewhere for a fully managed cloud IDE, mature team governance, or broad enterprise deployment controls.

Back

Information

Websitegithub.com
OrganizationsDyad Tech, Inc.
Authorsdyad-sh
Published date2025/04/11

More Items

AI Client2026

Hyper-Extract

Yifan Feng

Transforms unstructured documents into strongly-typed Knowledge Abstracts with one CLI command, extracting entities and relations into graphs, hypergraphs, and spatio‑temporal structures. Includes 80+ templates, multiple RAG engines, local vLLM support, Obsidian export and an MCP server.

cli python llm RAG embeddings+8

AI Agent2026

OpenHarness

HKUDS

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

agent-skills mcp mcp-client ai-agent cli+10

AI Model2026

Bonsai Demo

PrismML-Eng, PrismML

Runs the Bonsai family of quantized LLMs locally (including vision-capable 27B): provides scripts and demo UIs to run 1-bit and ternary Bonsai models on macOS (Metal), Linux/Windows (CUDA/Vulkan/ROCm), or CPU, with long context, tool-calling and an optional Open WebUI agent demo.

llm vision multimodal huggingface github+5